{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:49:52Z","timestamp":1791352192882,"version":"4.3.1"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate recognition of movement disorders (MDs) phenomenology remains a demanding task in pediatric practice, compounded by mixed and evolving motor presentations, inter-examiner expertise variability, and the scarcity of structured digital tools validated across age groups. A child with combined MDs may receive different phenomenological diagnoses from different examiners, with direct consequences for etiological guidance, treatment planning, neuromodulation candidacy, and longitudinal monitoring. Video-based examination is already central to expert practice, but its systematic analysis remains frequently inaccessible because of limited human resources.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and externally test a video-based framework for simultaneous detection of hyperkinetic MDs phenomenologies: dystonia, tremor, myoclonus, chorea, athetosis, ballismus, stereotypies, and tics using routine clinical recordings, with external, cross-cohort transfer from adult to pediatric populations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this proof-of-concept study, the framework combines markerless pose estimation, kinematic descriptors, and a pretrained foundation model. A shared predictive backbone was developed on 21 adults with confirmed hyperkinetic MDs and 4 healthy controls. External validation was performed on an independent cohort: a real-world pediatric sample (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f12, monogenic combined MDs). For the external dataset, the backbone was deployed without retraining; lightweight calibration adjusted only the final subject-level decision step using a clinician-labeled small representative subset of patients.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      After local calibration of the decision layer on the clinician-selected subset, performance improved on the held-out pediatric patients (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f7): Hamming accuracy rose from 0.804 to 0.839 and the Jaccard index from 0.548 to 0.633 (true positives 8 to 13, false negatives 9 to 4, false positives 2 to 5, across 56 patient-phenomenology decisions). Given the small held-out sample, these estimates should be regarded as exploratory. This calibrated performance was preserved, and the Jaccard index further improved, when the evaluation was restricted to the phenomenologies with more definite clinician agreement (Hamming accuracy 0.9, Jaccard index 0.786), indicating that the gains did not rest on the least-reliable labels.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A two-stage strategy, a reusable predictive backbone combined with lightweight, site-specific adaptation, may offer a practical and scalable route to routine-video-based digital phenotyping of MDs across age groups. A shared backbone trained on standardized adult recordings transferred phenotyping signal to an independent, real-world pediatric cohort without retraining. Local calibration of the decision layer improved performance in this small exploratory cohort, while clinical-grade reliability across the full phenotypic spectrum remains to be confirmed in larger cohorts.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1904458","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:50:16Z","timestamp":1791348616000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Simultaneous hyperkinetic movement disorders phenotyping: a cross-cohort pediatric transfer study using routine videos, markerless pose estimation and a tabular foundation model"],"prefix":"10.3389","volume":"17","author":[{"given":"Laura","family":"Cif","sequence":"first","affiliation":[{"name":"Service of Neurology, Department of Clinical Neurosciences, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL)","place":["Lausanne, Switzerland"]},{"name":"Institut du Neurone","place":["Montferrier sur Lez, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diane","family":"Demailly","sequence":"additional","affiliation":[{"name":"Institut du Neurone","place":["Montferrier sur Lez, France"]},{"name":"Department of Neurology, Clinique Beau Soleil, Institut Mutualiste Montpelli\u00e9rain","place":["Montpellier, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zohra","family":"Souei","sequence":"additional","affiliation":[{"name":"Institut du Neurone","place":["Montferrier sur Lez, France"]},{"name":"Department of Neurosurgery, Military University Hospital of Sfax","place":["Sfax, Tunisia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Mushhood Ur Rehman","sequence":"additional","affiliation":[{"name":"Edinburgh Medical School, University of Edinburgh","place":["Edinburgh, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Dario","family":"Ortigoza-Escobar","sequence":"additional","affiliation":[{"name":"Movement Disorders Unit, Pediatric Neurology Department, Institut de Recerca, Hospital Sant Joan de D\u00e9u","place":["Barcelona, Spain"]},{"name":"European Reference Network for Rare Neurological Diseases (ERN-RND)","place":["Barcelona, Spain"]},{"name":"U-703 Centre for Biomedical Research on Rare Diseases (CIBER-ER), Instituto de Salud Carlos III","place":["Barcelona, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mayt\u00e9","family":"Castro-Jim\u00e9nez","sequence":"additional","affiliation":[{"name":"Service of Neurology, Department of Clinical Neurosciences, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL)","place":["Lausanne, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"C\u00e9cile A.","family":"Hubsch","sequence":"additional","affiliation":[{"name":"Service of Neurology, Department of Clinical Neurosciences, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL)","place":["Lausanne, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sophie","family":"Huby","sequence":"additional","affiliation":[{"name":"Department of Neurology, CHU Montpellier","place":["Montpellier, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Morgan","family":"Dornadic","sequence":"additional","affiliation":[{"name":"Department of Neurology, CHU Montpellier","place":["Montpellier, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gun-Marie","family":"Hariz","sequence":"additional","affiliation":[{"name":"Department of Clinical Neuroscience, Ume\u00e5 University","place":["Ume\u00e5, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eduardo M.","family":"Moraud","sequence":"additional","affiliation":[{"name":"Defitech Center for Interventional Neurotherapies (NeuroRestore), University Hospital Lausanne and Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne","place":["Lausanne, Switzerland"]},{"name":"Neuro-X Institute, Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne","place":["Geneva, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jocelyne","family":"Bloch","sequence":"additional","affiliation":[{"name":"Defitech Center for Interventional Neurotherapies (NeuroRestore), University Hospital Lausanne and Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne","place":["Lausanne, Switzerland"]},{"name":"Department of Neurosurgery, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL)","place":["Lausanne, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabriella A.","family":"Horv\u00e0th","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, British Columbia Children\u2019s Hospital","place":["Vancouver, BC, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xavier","family":"Vasques","sequence":"additional","affiliation":[{"name":"Institut du Neurone","place":["Montferrier sur Lez, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1600018","DOI":"10.3389\/fneur.2025.1600018","article-title":"Editorial: digital biomarkers in movement disorders","volume":"16","author":"Stephen","year":"2025","journal-title":"Front Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1111\/dmcn.14721","article-title":"Diagnostic approach to paediatric movement disorders: a clinical practice guide","volume":"63","author":"Brandsma","year":"2021","journal-title":"Dev Med Child Neurol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1002\/mds.29584","article-title":"Between nothing and everything: phenomenology in movement disorders","volume":"38","author":"Sadnicka","year":"2023","journal-title":"Mov Disord"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"659805","DOI":"10.3389\/fneur.2021.659805","article-title":"Treatable hyperkinetic movement disorders not to be missed","volume":"12","author":"M\u00e9neret","year":"2021","journal-title":"Front Neurol"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1002\/acn3.70474","article-title":"Deep learning pose estimation for phenotyping of co-occuring hyperkinetic movement disorders","author":"Cif","year":"2026","journal-title":"Ann Clin Transl Neurol"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-026-03015-4","article-title":"Artificial intelligence in deep brain stimulation for movement disorders: a systematic review and technology readiness assessment","author":"Souei","year":"2026","journal-title":"Npj Digit Med"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"102952","DOI":"10.1016\/j.artmed.2024.102952","article-title":"Automatic two-dimensional & three-dimensional video analysis with deep learning for movement disorders: a systematic review","volume":"156","author":"Tang","year":"2024","journal-title":"Artif Intell Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"2046","DOI":"10.1002\/mds.30327","article-title":"Video-based data-driven models for diagnosing movement disorders: review and future directions","volume":"40","author":"Mart\u00ednez-Garc\u00eda-Pe\u00f1a","year":"2025","journal-title":"Mov Disord"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1186\/s12984-023-01186-9","article-title":"A systematic review of the applications of markerless motion capture (MMC) technology for clinical measurement in rehabilitation","volume":"20","author":"Lam","year":"2023","journal-title":"J NeuroEngineering Rehabil"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"884384","DOI":"10.3389\/frsip.2022.884384","article-title":"Deep learning based markerless motion tracking as a clinical tool for movement disorders: utility, feasibility and early experience","volume":"2","author":"Tien","year":"2022","journal-title":"Front Signal Process"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1335251","DOI":"10.3389\/fbioe.2023.1335251","article-title":"Effective evaluation of HGcnMLP method for markerless 3D pose estimation of musculoskeletal diseases patients based on smartphone monocular video","volume":"11","author":"Hu","year":"2024","journal-title":"Front Bioeng Biotechnol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1649330","DOI":"10.3389\/fphys.2025.1649330","article-title":"Commercial vision sensors and AI-based pose estimation frameworks for markerless motion analysis in sports and exercises: a mini review","volume":"16","author":"Edriss","year":"2025","journal-title":"Front Physiol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","article-title":"Accurate predictions on small data with a tabular foundation model","volume":"637","author":"Hollmann","year":"2025","journal-title":"Nature"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2602.11139","article-title":"TabICLv2: a better, faster, scalable, and open tabular foundation model","author":"Qu","year":"2026","journal-title":"arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2502.05564","article-title":"TabICL: a tabular foundation model for in-context learning on large data","author":"Qu","year":"2025","journal-title":"arXiv"},{"key":"ref16","first-page":"779","author":"Redmon","year":"2016"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Lin","year":"2014"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/0167-2789(88)90081-4","article-title":"Approach to an irregular time series on the basis of the fractal theory","volume":"31","author":"Higuchi","year":"1988","journal-title":"Phys Nonlinear Phenom"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"174102","DOI":"10.1103\/PhysRevLett.88.174102","article-title":"Permutation entropy: a natural complexity measure for time series","volume":"88","author":"Bandt","year":"2002","journal-title":"Phys Rev Lett"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat Methods"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.08172","article-title":"Mediapipe: a framework for building perception pipelines","author":"Lugaresi","year":"2019","journal-title":"arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1812.08008","article-title":"Openpose: realtime multi-person 2D pose estimation using part affinity fields","author":"Cao","year":"2018","journal-title":"arXiv"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1002\/mdc3.70123","article-title":"Computer vision Technologies in Movement Disorders: a systematic review","volume":"12","author":"Pecoraro","year":"2025","journal-title":"Mov Disord Clin Pract"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"100649","DOI":"10.1016\/j.cobme.2026.100649","article-title":"Trustworthy AI in medical image analysis: a unified perspective built on robustness and layers of trust","volume":"37","author":"Zuluaga","year":"2026","journal-title":"Curr Opin Biomed Eng"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"104902","DOI":"10.1016\/j.jbi.2025.104902","article-title":"Strategies for detecting and mitigating dataset shift in machine learning for health predictions: a systematic review","volume":"170","author":"Silva","year":"2025","journal-title":"J Biomed Inform"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.03971","article-title":"Real-TabPFN: improving tabular foundation models via continued pre-training with real-world data","author":"Garg","year":"2025","journal-title":"arXiv"},{"key":"ref27","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt","year":"2000","journal-title":"Adv Large Margin Classif"},{"key":"ref28","first-page":"694","author":"Zadrozny","year":"2002"},{"key":"ref29","first-page":"625","author":"Niculescu-Mizil","year":"2005"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1904458\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:50:29Z","timestamp":1791348629000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1904458\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":29,"alternative-id":["10.3389\/fneur.2026.1904458"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1904458","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1904458"}}